Skip to content Accessibility statement

AI-generated music inferior to human-composed works, according to study

News

Posted on Tuesday 4 April 2023

Researchers at the University of York have found that current AI-generated music is inferior to human-composed music.
The researchers have produced guidelines for comparative evaluation of machine learning systems

They also showed that there are faults with the algorithms used in AI music generation that could infringe on copyright, and developed guidelines to help others evaluate the systems they are using.

In the study, 50 participants with a high level of musical knowledge, were played excerpts of music - some from real human-composed works, and others generated by deep learning (DL), a type of artificial neural network, and non-DL algorithms.

The study recruited participants who had experience in analysing note content and stylistic success in music so that results were not just focused on expression in music.

Musical critera

The listeners were asked to rate the excerpts along six musical criteria: stylistic success, aesthetic pleasure, repetition or self-reference, melody, harmony, and rhythm, but were not told the identity of what they are listening to - human-composed or computer-generated.

Co-author, Dr Tom Collins, from the School of Arts and Creative Technologies at the University of York, said: “On analysis, the ratings for human-composed excerpts are significantly higher and stylistically more successful than those for any of the systems responsible for computer-generated excerpts.”

The study also provided findings that raise concerns about the potential ethical violations of direct copying with deep learning methods. A popular type of DL architecture called transformer (the same type of architecture as behind OpenAI's ChatGPT) was shown to copy large chunks of training data in its output.

Legal and ethical

Dr Collins explained: “If Artist X uses an AI-generated excerpt, the algorithm that generates the excerpt may happen to copy a chunk of a song in the training (input) data by Artist Y. Unwittingly, if Artist X releases their song, they are infringing the copyright of Artist Y. 

“It is a concerning finding and perhaps suggests that organisations who develop the algorithms should be being policed in some way or should be policing themselves. They know there are issues with these algorithms, so the focus should be on rectifying this so that AI-generated content can continue to be produced, but in an ethical and legal way."

The researchers in the study have provided seven guidelines for conducting a comparative evaluation of machine learning systems. The findings could help to improve the development of AI-generated music, address current ethical issues, and avoid future legal dilemmas around copyright infringement.

Further information

Example of human-composed music: Joseph Haydn's String quartet in F minor op.20 no.5 (Hob.III:35), 1st movement bars 35-48.

Example of music generated by Deep Learning algorithm: Music Transformer (Huang et al., 2018).

Example of music generated by non-Deep Learning algorithm: MAIA Markov algorithm (Collins & Laney, 2017).

Example of music generated by another Deep Learning algorithm: Listen to Transformer, constituting a near-exact copy of a well-known piece called "Carol of the bells."

Research newsletter

Our monthly research newsletter features a curated mix of news, events, and recent discoveries delivered straight to your inbox.

Sign up

Explore more news

News

11 November 2026

The University of York and NatWest have unveiled a new Life Sciences Business Accelerator to turn academic breakthroughs into real-world health and environmental solutions.

News

10 November 2026

New research has shown that patients who receive care from both NHS and private hospitals need better protection against problems with quality and safety.

News

6 November 2026

The Minister for Science, Innovation and Investment, Chris McDonald MP, visited York’s historic Guildhall to learn how the University is driving economic growth and innovation across the region.

News

6 November 2026

The University of York has officially joined the UK Reproducibility Network (UKRN) as an institutional member, reinforcing its commitment to the highest standards of research rigour, transparency and inclusivity.

News

5 November 2026

The UK Government has lowered a key investment value, known as the headline social discount rate, from 3.5% to 3% following landmark research, giving greater weight to long-term environmental preservation, transport and hospital projects.

Read more news